PM2.5浓度空间估算的神经网络与克里格方法对比  

Performance Comparison of Artificial Neural Network and Kriging in Spatial Estimation of PM Concentration

作　　者：许珊[1] 邹滨[1] 王敏 刘宁[1] XU Shan;ZOU Bin;WANG Min;LIU Ning(School of Geosciences and Info-Physics,Central South University,Changsha 410083,China;The Third Surveying and Mapping Institute of Hunan Province,Changsha 410004,China)

机构地区：[1]中南大学地球科学与信息物理学院,湖南长沙410083 [2]湖南省第三测绘院,湖南长沙410004

出　　处：《武汉大学学报（信息科学版）》2020年第10期1642-1650,共9页Geomatics and Information Science of Wuhan University

基　　金：国家重点研发计划(2016YFC0206205);国家自然科学基金(41871317);中南大学创新驱动计划(2018CX016)。

摘　　要：针对人工神经网络与克里格插值在PM2.5浓度空间估算中精度随样本点数量与耦合因素不同差异较大的问题,基于相关分析与径向基函数(radical basis function, RBF)筛选PM2.5空间变异关键影响因素,对比不同比例训练样本下普通克里格插值(ordinary Kriging, OK),仅考虑地理坐标RBF神经网络,耦合关键因素的协同克里格插值(CoKriging, CK)及RBF神经网络(CoRBF)的效果差异,并基于最优方法开展PM2.5浓度空间制图。结果表明:4种方法均能有效实现PM2.5浓度空间估算,且精度随训练样本比例增大而波动上升。考虑关键因素人口密度的CoRBF最能表现数据变化趋势,而CK在误差指标上更优越。基于CK与CoRBF的PM2.5浓度空间估算结果较好展示了污染的分异特征,前者较后者更平滑。Performance of artificial neural network modeling and Kriging interpolation in PM2.5 concentration estimation varies with sample sizes and predictor variables change. This paper analyzes the performance of ordinary Kriging(OK), radical basis function(RBF) networks based on geographic coordinates,CoKriging and RBF with the key factor(s)(CK and CoRBF) selected by correlation analysis and RBF network, using different training sets with various sizes. The spatial distribution of PM2.5 concentration is then estimated by the best performed method. Results show that RBF, CoRBF, OK, and CK can all be used to estimate PM2.5 concentration efficiently, and their accuracies improved unstably as the number of training sites increase. CoRBF with the key factor of population illustrates the largest variation of PM2.5 concentration, while CK has the highest coefficient of determination(R2) and index of agreement(IOA) and the lowest mean square error(MSE), mean absolute error(MAE), and relative error(RE). Correspondingly, the spatial pattern of CK estimated PM2.5 concentration is smoother than CoRBF estimated PM2.5 concentration, while they both are very similar to site measurements and reveal detailed information.

关 键 词：径向基函数 人工神经网络 克里格插值 大气污染 空间估算 

分 类 号：P208[天文地球—地图制图学与地理信息工程]